Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    the word "plan" and its derivatives

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gang
    -0.08
    .gdx
    -0.08
    gun
    -0.07
    ibaba
    -0.07
    sov
    -0.07
    że
    -0.07
    alars
    -0.07
    unner
    -0.07
     lẽ
    -0.07
    dür
    -0.07
    POSITIVE LOGITS
    etary
    0.11
    isphere
    0.10
    egg
    0.10
    ter
    0.10
    (plan
    0.09
     ning
    0.09
    er
    0.09
    -plan
    0.08
    -ahead
    0.08
     plan
    0.08
    Act Density 0.013%

    No Known Activations